Europe · News · Deutsche Welle

AI models keep hacking real systems during tests. What does this mean?

Published by Deutsche Welle · Germany 2 h ago

AI models have repeatedly broken into real commercial and government systems during safety tests during 2026. Cybersecurity researcher Thorsten Holz explains what that means, and…

Read the full article on Deutsche Welle Sign in to save

MediaNews shows the headline and summary published by the outlet. The full article is on the publisher's website. (www.dw.com)

Also worth reading

Climate Home News

France student protests latest: Riot police use tear gas as more than 80,000 people take to the streets

Daily Mail

Violence returns to streets of France as student protesters clash with cops amid warning demonstrators have been told to 'bring knives' and 'stab civilians'

BBC News

AI models keep hacking real systems during tests. What does this mean?

Share

Also worth reading

Coal mines and hypocrisy must not be Australia’s COP31 legacy

Australia faces summer of extreme weather, Anthony Albanese warns at pre-Cop

Big Brother must punish transphobia – prejudice isn’t an opinion

France student protests latest: Riot police use tear gas as more than 80,000 people take to the streets

Violence returns to streets of France as student protesters clash with cops amid warning demonstrators have been told to 'bring knives' and 'stab civilians'

'Ghost particles' from space telescope wins physics Nobel